© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134917
    Prev
    Next
    INDEX
    Explanations

    Anjuna area

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    س
    1.66
    t
    1.54
     that
    1.34
    -
    1.33
    et
    1.30
    \
    1.22
    ä
    1.19
    en
    1.18
    I
    1.18
    '
    1.15
    POSITIVE LOGITS
    지로
    1.05
    取り組み
    1.02
     važ
    0.95
    Ⴖ
    0.94
    を経
    0.92
    вяза
    0.92
    ⟤
    0.92
    فك
    0.91
    май
    0.91
    филлер
    0.91
    Activations Density 0.000%

    No Known Activations